Li Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Li Zhu has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Junghui Chen
Department of Chemical Engineering, Chung-Yuan Christian University, Taoyuan, Taiwan
3 shared publications - Cheng Shao
Institute of Advanced Control Technology, Dalian University of Technology, Dalian 116024, China
2 shared publications - Xin Yang
Key Laboratory of Social Computing and Cognitive Intelligence, Ministry of Education, Dalian University of Technology, Dalian, China
2 shared publications - Ao Jin
Dalian University of Technology
1 shared publication - Chun-I. Chen
Western Digital Corporation, Magnetic Head Wafer Manufacturing Fab, Advanced Process Control Group, Fremont, CA, USA
1 shared publication - Hongye Su
Zhejiang University
1 shared publication
Latest Publications
- 25 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (8) , 5187-5201
ICAD: Rethinking the Role of Inference and Cues for the Anomaly Detection of Time Series in IIoT
Time series anomaly detection in real-world Industrial Internet of Things (IIoT) systems is pivotal for identifying unsafe conditions and implementing timely preventive measures. While diffusion models are popular for capturing complex patterns, they often struggle to balance diversity and fidelity across scenarios due to limited exploration of context-window logical inference relationships and trend-pattern cues. To address these challenges, we propose ICAD, a novel method that rethinks the role of inference and cues in IIoT time series anomaly detection. ICAD defines trend patterns and uncertainties in textual form and utilizes a fine-tuned large language model to encode these descriptions as conditions for the diffusion model, thereby enhancing its generalization across diverse data distributions. Additionally, a “reasoning network for contextual window” mechanism is designed to capture temporal dependencies between adjacent windows, complemented by multi-scale and spatial feature adaptive fusion modules to further enhance the predictive performance. Empirical evaluations across four benchmark datasets and a large-scale ethylene oxide production process demonstrate that ICAD consistently outperforms state-of-the-art baselines, confirming its effectiveness and practicality in overcoming current anomaly detection model limitations.
- 25 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (8) , 5187-5201
ICAD: Rethinking the Role of Inference and Cues for the Anomaly Detection of Time Series in IIoT
Time series anomaly detection in real-world Industrial Internet of Things (IIoT) systems is pivotal for identifying unsafe conditions and implementing timely preventive measures. While diffusion models are popular for capturing complex patterns, they often struggle to balance diversity and fidelity across scenarios due to limited exploration of context-window logical inference relationships and trend-pattern cues. To address these challenges, we propose ICAD, a novel method that rethinks the role of inference and cues in IIoT time series anomaly detection. ICAD defines trend patterns and uncertainties in textual form and utilizes a fine-tuned large language model to encode these descriptions as conditions for the diffusion model, thereby enhancing its generalization across diverse data distributions. Additionally, a “reasoning network for contextual window” mechanism is designed to capture temporal dependencies between adjacent windows, complemented by multi-scale and spatial feature adaptive fusion modules to further enhance the predictive performance. Empirical evaluations across four benchmark datasets and a large-scale ethylene oxide production process demonstrate that ICAD consistently outperforms state-of-the-art baselines, confirming its effectiveness and practicality in overcoming current anomaly detection model limitations.
- 13 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23 (15455955) , 9107-9118
Enhancing Quality Prediction in Industrial Processes With Spatiotemporal Attention-Based Data Techniques
The intricate and dynamic characteristics of time series data in industrial processes necessitates sophisticated data-driven soft sensor methodologies for modeling. However, the performance of such models often heavily hinges data quality, leading to potential neglect of critical spatial and temporal correlations essential for comprehending model behavior. To address these challenges, this study proposes a novel approach integrating spatiotemporal-based graph convolutional networks with attention-based preprocessing for soft sensor modeling. This framework not only enhances model reliability by extracting high-quality time series data but also captures localized spatiotemporal correlations vital for comprehending the intricate interactions among variables in the soft sensor. Additionally, the integration of attention-based preprocessing enables adaptive updates to the soft sensor model, thereby ensuring accurate prediction of process quality. The effectiveness and applicability of the proposed method are demonstrated through experimentation on both simulated processes and real-world applications in the ethylene oxide industry. Importantly, this data-driven approach to constructing transfer entropy aligns with fundamental a priori knowledge, enhancing the interpretability of the model results.
- 13 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23 (15455955) , 9107-9118
Enhancing Quality Prediction in Industrial Processes With Spatiotemporal Attention-Based Data Techniques
The intricate and dynamic characteristics of time series data in industrial processes necessitates sophisticated data-driven soft sensor methodologies for modeling. However, the performance of such models often heavily hinges data quality, leading to potential neglect of critical spatial and temporal correlations essential for comprehending model behavior. To address these challenges, this study proposes a novel approach integrating spatiotemporal-based graph convolutional networks with attention-based preprocessing for soft sensor modeling. This framework not only enhances model reliability by extracting high-quality time series data but also captures localized spatiotemporal correlations vital for comprehending the intricate interactions among variables in the soft sensor. Additionally, the integration of attention-based preprocessing enables adaptive updates to the soft sensor model, thereby ensuring accurate prediction of process quality. The effectiveness and applicability of the proposed method are demonstrated through experimentation on both simulated processes and real-world applications in the ethylene oxide industry. Importantly, this data-driven approach to constructing transfer entropy aligns with fundamental a priori knowledge, enhancing the interpretability of the model results.
- 30 May 2025
- Published by Elsevier in ISA Transactions
- Vol. 164, 297-309
Distributed formation control for port-Hamiltonian multi-agent systems by average state estimation
- 30 May 2025
- Published by Elsevier in ISA Transactions
- Vol. 164, 297-309
Distributed formation control for port-Hamiltonian multi-agent systems by average state estimation
- 6 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 54 (6) , 3450-3460
Prognostics for Semiconductor Sustainability: Tool Failure Behavior Prediction in Fabrication Processes
Semiconductor fabrication is regarded as one of the most complicated production processes with a high-mixed and uncertain production context, and it suffers from tool failures. Prognostics can predict the time when a process tool cannot perform its intended function. Therefore, preventive maintenance can be planned in time with the minimum impact on the production lines. Because most of the tool faults cannot be owed to the failure of a single component, it is challenging to model the system directly through mechanism analysis. Therefore, the development of failure prognostics in semiconductor manufacturing is somewhat impeded. Data-driven approaches are appropriate in this case, especially when the domain knowledge of the system under study is not comprehensive enough. This article attempts to propose a novel data-driven prognostic method integrated with the auto-associative regression and the Gaussian process to address the issue. This proposed method can extract the failure factors, establish the prognostic model and present the reliability of the model. On the basis of the built prognostic model, the failure tendency is predicted and the maintenance schedule can be determined. The validity and feasibility of the proposed method are demonstrated through a numerical example and a practical semiconductor manufacturing process, respectively. The proposed prognostic scheme can guide the frequency plan of preventive maintenance in the fabrication process and improve the productivity in semiconductor manufacturing.
- 6 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 54 (6) , 3450-3460
Prognostics for Semiconductor Sustainability: Tool Failure Behavior Prediction in Fabrication Processes
Semiconductor fabrication is regarded as one of the most complicated production processes with a high-mixed and uncertain production context, and it suffers from tool failures. Prognostics can predict the time when a process tool cannot perform its intended function. Therefore, preventive maintenance can be planned in time with the minimum impact on the production lines. Because most of the tool faults cannot be owed to the failure of a single component, it is challenging to model the system directly through mechanism analysis. Therefore, the development of failure prognostics in semiconductor manufacturing is somewhat impeded. Data-driven approaches are appropriate in this case, especially when the domain knowledge of the system under study is not comprehensive enough. This article attempts to propose a novel data-driven prognostic method integrated with the auto-associative regression and the Gaussian process to address the issue. This proposed method can extract the failure factors, establish the prognostic model and present the reliability of the model. On the basis of the built prognostic model, the failure tendency is predicted and the maintenance schedule can be determined. The validity and feasibility of the proposed method are demonstrated through a numerical example and a practical semiconductor manufacturing process, respectively. The proposed prognostic scheme can guide the frequency plan of preventive maintenance in the fabrication process and improve the productivity in semiconductor manufacturing.
- 15 November 2023
- Published by Springer Nature
- p. 175-187
Spiking Reinforcement Learning for Weakly-Supervised Anomaly Detection
- 15 November 2023
- Published by Springer Nature
- p. 175-187
Spiking Reinforcement Learning for Weakly-Supervised Anomaly Detection
- Open Access
An Ensemble Learning Method for Robot Electronic Nose with Active Perception
The electronic nose is the olfactory organ of the robot, which is composed of a large number of sensors to perceive the smell of objects through free diffusion. Traditionally, it is difficult to realize the active perception function, and it is difficult to meet the requirements of small size, low cost, and quick response that robots require. In order to address these issues, a novel electronic nose with active perception was designed and an ensemble learning method was proposed to distinguish the smell of different objects. An array of three MQ303 semiconductor gas sensors and an electrochemical sensor DART-2-Fe5 were used to construct the novel electronic nose, and the proposed ensemble learning method with four algorithms realized the active odor perception function. The experiment results verified that the accuracy of the active odor perception can reach more than 90%, even though it used 30% training data. The novel electronic nose with active perception based on the ensemble learning method can improve the efficiency and accuracy of odor data collection and olfactory perception.
Open AccessAn Ensemble Learning Method for Robot Electronic Nose with Active Perception
The electronic nose is the olfactory organ of the robot, which is composed of a large number of sensors to perceive the smell of objects through free diffusion. Traditionally, it is difficult to realize the active perception function, and it is difficult to meet the requirements of small size, low cost, and quick response that robots require. In order to address these issues, a novel electronic nose with active perception was designed and an ensemble learning method was proposed to distinguish the smell of different objects. An array of three MQ303 semiconductor gas sensors and an electrochemical sensor DART-2-Fe5 were used to construct the novel electronic nose, and the proposed ensemble learning method with four algorithms realized the active odor perception function. The experiment results verified that the accuracy of the active odor perception can reach more than 90%, even though it used 30% training data. The novel electronic nose with active perception based on the ensemble learning method can improve the efficiency and accuracy of odor data collection and olfactory perception.
- 2 March 2019
- Published by Elsevier in Journal of Cleaner Production
- Vol. 222, 695-709
Integrated scheduling of a hybrid manufacturing and recovering system in a multi-product multi-stage environment with carbon emission
- 2 March 2019
- Published by Elsevier in Journal of Cleaner Production
- Vol. 222, 695-709
Integrated scheduling of a hybrid manufacturing and recovering system in a multi-product multi-stage environment with carbon emission
- 21 December 2018
- Published by Wiley in International Journal of Energy Research
- Vol. 43 (2) , 814-828
Development of energy efficiency principal component analysis model for factor extraction and efficiency evaluation in large-scale chemical processes
- 21 December 2018
- Published by Wiley in International Journal of Energy Research
- Vol. 43 (2) , 814-828
Development of energy efficiency principal component analysis model for factor extraction and efficiency evaluation in large-scale chemical processes